diff options
Diffstat (limited to 'include/linux/netdevice.h')
| -rw-r--r-- | include/linux/netdevice.h | 229 |
1 files changed, 146 insertions, 83 deletions
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 70ad0291d517..779b23595596 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -41,7 +41,6 @@ #include <linux/ethtool.h> #include <net/net_namespace.h> -#include <net/dsa.h> #ifdef CONFIG_DCB #include <net/dcbnl.h> #endif @@ -57,6 +56,8 @@ struct netpoll_info; struct device; struct phy_device; +struct dsa_switch_tree; + /* 802.11 specific */ struct wireless_dev; /* 802.15.4 specific */ @@ -236,8 +237,7 @@ struct netdev_hw_addr_list { netdev_hw_addr_list_for_each(ha, &(dev)->mc) struct hh_cache { - u16 hh_len; - u16 __pad; + unsigned int hh_len; seqlock_t hh_lock; /* cached hardware header; allow for machine alignment needs. */ @@ -330,6 +330,7 @@ struct napi_struct { enum { NAPI_STATE_SCHED, /* Poll is scheduled */ + NAPI_STATE_MISSED, /* reschedule a napi */ NAPI_STATE_DISABLE, /* Disable pending */ NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */ @@ -338,12 +339,13 @@ enum { }; enum { - NAPIF_STATE_SCHED = (1UL << NAPI_STATE_SCHED), - NAPIF_STATE_DISABLE = (1UL << NAPI_STATE_DISABLE), - NAPIF_STATE_NPSVC = (1UL << NAPI_STATE_NPSVC), - NAPIF_STATE_HASHED = (1UL << NAPI_STATE_HASHED), - NAPIF_STATE_NO_BUSY_POLL = (1UL << NAPI_STATE_NO_BUSY_POLL), - NAPIF_STATE_IN_BUSY_POLL = (1UL << NAPI_STATE_IN_BUSY_POLL), + NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED), + NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), + NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), + NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), + NAPIF_STATE_HASHED = BIT(NAPI_STATE_HASHED), + NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), + NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), }; enum gro_result { @@ -352,6 +354,7 @@ enum gro_result { GRO_HELD, GRO_NORMAL, GRO_DROP, + GRO_CONSUMED, }; typedef enum gro_result gro_result_t; @@ -413,20 +416,7 @@ static inline bool napi_disable_pending(struct napi_struct *n) return test_bit(NAPI_STATE_DISABLE, &n->state); } -/** - * napi_schedule_prep - check if NAPI can be scheduled - * @n: NAPI context - * - * Test if NAPI routine is already running, and if not mark - * it as running. This is used as a condition variable to - * insure only one NAPI poll instance runs. We also make - * sure there is no pending NAPI disable. - */ -static inline bool napi_schedule_prep(struct napi_struct *n) -{ - return !napi_disable_pending(n) && - !test_and_set_bit(NAPI_STATE_SCHED, &n->state); -} +bool napi_schedule_prep(struct napi_struct *n); /** * napi_schedule - schedule NAPI poll @@ -463,7 +453,6 @@ static inline bool napi_reschedule(struct napi_struct *napi) return false; } -bool __napi_complete(struct napi_struct *n); bool napi_complete_done(struct napi_struct *n, int work_done); /** * napi_complete - NAPI processing complete @@ -797,11 +786,11 @@ struct tc_cls_u32_offload; struct tc_to_netdev { unsigned int type; union { - u8 tc; struct tc_cls_u32_offload *cls_u32; struct tc_cls_flower_offload *cls_flower; struct tc_cls_matchall_offload *cls_mall; struct tc_cls_bpf_offload *cls_bpf; + struct tc_mqprio_qopt *mqprio; }; bool egress_dev; }; @@ -818,22 +807,43 @@ enum xdp_netdev_command { * when it is no longer used. */ XDP_SETUP_PROG, + XDP_SETUP_PROG_HW, /* Check if a bpf program is set on the device. The callee should - * return true if a program is currently attached and running. + * set @prog_attached to one of XDP_ATTACHED_* values, note that "true" + * is equivalent to XDP_ATTACHED_DRV. */ XDP_QUERY_PROG, }; +struct netlink_ext_ack; + struct netdev_xdp { enum xdp_netdev_command command; union { /* XDP_SETUP_PROG */ - struct bpf_prog *prog; + struct { + u32 flags; + struct bpf_prog *prog; + struct netlink_ext_ack *extack; + }; /* XDP_QUERY_PROG */ - bool prog_attached; + struct { + u8 prog_attached; + u32 prog_id; + }; }; }; +#ifdef CONFIG_XFRM_OFFLOAD +struct xfrmdev_ops { + int (*xdo_dev_state_add) (struct xfrm_state *x); + void (*xdo_dev_state_delete) (struct xfrm_state *x); + void (*xdo_dev_state_free) (struct xfrm_state *x); + bool (*xdo_dev_offload_ok) (struct sk_buff *skb, + struct xfrm_state *x); +}; +#endif + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -910,15 +920,14 @@ struct netdev_xdp { * * int (*ndo_change_mtu)(struct net_device *dev, int new_mtu); * Called when a user wants to change the Maximum Transfer Unit - * of a device. If not defined, any request to change MTU will - * will return an error. + * of a device. * * void (*ndo_tx_timeout)(struct net_device *dev); * Callback used when the transmitter has not made any progress * for dev->watchdog ticks. * - * struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev, - * struct rtnl_link_stats64 *storage); + * void (*ndo_get_stats64)(struct net_device *dev, + * struct rtnl_link_stats64 *storage); * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); * Called when a user wants to get the network device usage * statistics. Drivers must do one of the following: @@ -968,11 +977,12 @@ struct netdev_xdp { * with PF and querying it may introduce a theoretical security risk. * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); - * int (*ndo_setup_tc)(struct net_device *dev, u8 tc) - * Called to setup 'tc' number of traffic classes in the net device. This - * is always called from the stack with the rtnl lock held and netif tx - * queues stopped. This allows the netdevice to perform queue management - * safely. + * int (*ndo_setup_tc)(struct net_device *dev, u32 handle, u32 chain_index, + * __be16 protocol, struct tc_to_netdev *tc); + * Called to setup any 'tc' scheduler, classifier or action on @dev. + * This is always called from the stack with the rtnl lock held and netif + * tx queues stopped. This allows the netdevice to perform queue + * management safely. * * Fiber Channel over Ethernet (FCoE) offload functions. * int (*ndo_fcoe_enable)(struct net_device *dev); @@ -1104,12 +1114,6 @@ struct netdev_xdp { * by 'ndo_dfwd_add_station'. 'pdev' is the net device backing * the station and priv is the structure returned by the add * operation. - * netdev_tx_t (*ndo_dfwd_start_xmit)(struct sk_buff *skb, - * struct net_device *dev, - * void *priv); - * Callback to use for xmit over the accelerated station. This - * is used in place of ndo_start_xmit on accelerated net - * devices. * int (*ndo_set_tx_maxrate)(struct net_device *dev, * int queue_index, u32 maxrate); * Called when a user wants to set a max-rate limitation of specific @@ -1166,8 +1170,8 @@ struct net_device_ops { struct neigh_parms *); void (*ndo_tx_timeout) (struct net_device *dev); - struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev, - struct rtnl_link_stats64 *storage); + void (*ndo_get_stats64)(struct net_device *dev, + struct rtnl_link_stats64 *storage); bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id); int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, @@ -1184,9 +1188,6 @@ struct net_device_ops { struct netpoll_info *info); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif -#ifdef CONFIG_NET_RX_BUSY_POLL - int (*ndo_busy_poll)(struct napi_struct *dev); -#endif int (*ndo_set_vf_mac)(struct net_device *dev, int queue, u8 *mac); int (*ndo_set_vf_vlan)(struct net_device *dev, @@ -1220,7 +1221,7 @@ struct net_device_ops { struct net_device *dev, int vf, bool setting); int (*ndo_setup_tc)(struct net_device *dev, - u32 handle, + u32 handle, u32 chain_index, __be16 protocol, struct tc_to_netdev *tc); #if IS_ENABLED(CONFIG_FCOE) @@ -1309,9 +1310,6 @@ struct net_device_ops { void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv); - netdev_tx_t (*ndo_dfwd_start_xmit) (struct sk_buff *skb, - struct net_device *dev, - void *priv); int (*ndo_get_lock_subclass)(struct net_device *dev); int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, @@ -1431,13 +1429,14 @@ enum netdev_priv_flags { /** * struct net_device - The DEVICE structure. - * Actually, this whole structure is a big mistake. It mixes I/O - * data with strictly "high-level" data, and it has to know about - * almost every data structure used in the INET module. + * + * Actually, this whole structure is a big mistake. It mixes I/O + * data with strictly "high-level" data, and it has to know about + * almost every data structure used in the INET module. * * @name: This is the first field of the "visible" part of this structure * (i.e. as seen by users in the "Space.c" file). It is the name - * of the interface. + * of the interface. * * @name_hlist: Device name hash chain, please keep it close to name[] * @ifalias: SNMP alias @@ -1511,6 +1510,7 @@ enum netdev_priv_flags { * @max_mtu: Interface Maximum MTU value * @type: Interface hardware type * @hard_header_len: Maximum hardware header length. + * @min_header_len: Minimum hardware header length * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed @@ -1552,7 +1552,6 @@ enum netdev_priv_flags { * @ax25_ptr: AX.25 specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering * - * @last_rx: Time of last Rx * @dev_addr: Hw address (before bcast, * because most packets are unicast) * @@ -1594,8 +1593,8 @@ enum netdev_priv_flags { * @rtnl_link_state: This enum represents the phases of creating * a new link * - * @destructor: Called from unregister, - * can be used to call free_netdev + * @needs_free_netdev: Should unregister perform free_netdev? + * @priv_destructor: Called from unregister * @npinfo: XXX: need comments on this one * @nd_net: Network namespace this network device is inside * @@ -1709,6 +1708,10 @@ struct net_device { const struct ndisc_ops *ndisc_ops; #endif +#ifdef CONFIG_XFRM + const struct xfrmdev_ops *xfrmdev_ops; +#endif + const struct header_ops *header_ops; unsigned int flags; @@ -1728,6 +1731,7 @@ struct net_device { unsigned int max_mtu; unsigned short type; unsigned short hard_header_len; + unsigned char min_header_len; unsigned short needed_headroom; unsigned short needed_tailroom; @@ -1778,8 +1782,6 @@ struct net_device { /* * Cache lines mostly used on receive path (including eth_type_trans()) */ - unsigned long last_rx; - /* Interface address info used in eth_type_trans() */ unsigned char *dev_addr; @@ -1790,6 +1792,7 @@ struct net_device { unsigned int real_num_rx_queues; #endif + struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; @@ -1818,7 +1821,7 @@ struct net_device { #ifdef CONFIG_NET_SCHED DECLARE_HASHTABLE (qdisc_hash, 4); #endif - unsigned long tx_queue_len; + unsigned int tx_queue_len; spinlock_t tx_global_lock; int watchdog_timeo; @@ -1852,7 +1855,8 @@ struct net_device { RTNL_LINK_INITIALIZING, } rtnl_link_state:16; - void (*destructor)(struct net_device *dev); + bool needs_free_netdev; + void (*priv_destructor)(struct net_device *dev); #ifdef CONFIG_NETPOLL struct netpoll_info __rcu *npinfo; @@ -1869,8 +1873,12 @@ struct net_device { struct pcpu_vstats __percpu *vstats; }; +#if IS_ENABLED(CONFIG_GARP) struct garp_port __rcu *garp_port; +#endif +#if IS_ENABLED(CONFIG_MRP) struct mrp_port __rcu *mrp_port; +#endif struct device dev; const struct attribute_group *sysfs_groups[4]; @@ -1904,6 +1912,13 @@ struct net_device { }; #define to_net_dev(d) container_of(d, struct net_device, dev) +static inline bool netif_elide_gro(const struct net_device *dev) +{ + if (!(dev->features & NETIF_F_GRO) || dev->xdp_prog) + return true; + return false; +} + #define NETDEV_ALIGN 32 static inline @@ -2014,15 +2029,6 @@ void dev_net_set(struct net_device *dev, struct net *net) write_pnet(&dev->nd_net, net); } -static inline bool netdev_uses_dsa(struct net_device *dev) -{ -#if IS_ENABLED(CONFIG_NET_DSA) - if (dev->dsa_ptr != NULL) - return dsa_uses_tagged_protocol(dev->dsa_ptr); -#endif - return false; -} - /** * netdev_priv - access network device private data * @dev: network device @@ -2448,6 +2454,7 @@ static inline int dev_recursion_level(void) struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); +struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb); @@ -2565,9 +2572,7 @@ static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_gro_checksum_validate_complete(skb, \ compute_pseudo(skb, proto)); \ - if (__ret) \ - __skb_mark_checksum_bad(skb); \ - else \ + if (!__ret) \ skb_gro_incr_csum_unnecessary(skb); \ __ret; \ }) @@ -2667,6 +2672,19 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, remcsum_unadjust((__sum16 *)ptr, grc->delta); } +#ifdef CONFIG_XFRM_OFFLOAD +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) +{ + if (PTR_ERR(pp) != -EINPROGRESS) + NAPI_GRO_CB(skb)->flush |= flush; +} +#else +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) +{ + NAPI_GRO_CB(skb)->flush |= flush; +} +#endif + static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, @@ -2694,6 +2712,8 @@ static inline bool dev_validate_header(const struct net_device *dev, { if (likely(len >= dev->hard_header_len)) return true; + if (len < dev->min_header_len) + return false; if (capable(CAP_SYS_RAWIO)) { memset(ll_header + len, 0, dev->hard_header_len - len); @@ -3107,7 +3127,19 @@ static inline bool netif_subqueue_stopped(const struct net_device *dev, return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb)); } -void netif_wake_subqueue(struct net_device *dev, u16 queue_index); +/** + * netif_wake_subqueue - allow sending packets on subqueue + * @dev: network device + * @queue_index: sub queue index + * + * Resume individual transmit queue of a device with multiple transmit queues. + */ +static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) +{ + struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); + + netif_tx_wake_queue(txq); +} #ifdef CONFIG_XPS int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, @@ -3252,6 +3284,7 @@ void __dev_notify_flags(struct net_device *, unsigned int old_flags, int dev_change_name(struct net_device *, const char *); int dev_set_alias(struct net_device *, const char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); +int __dev_set_mtu(struct net_device *, int); int dev_set_mtu(struct net_device *, int); void dev_set_group(struct net_device *, int); int dev_set_mac_address(struct net_device *, struct sockaddr *); @@ -3261,10 +3294,15 @@ int dev_get_phys_port_id(struct net_device *dev, int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); int dev_change_proto_down(struct net_device *dev, bool proto_down); -int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); + +typedef int (*xdp_op_t)(struct net_device *dev, struct netdev_xdp *xdp); +int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, + int fd, u32 flags); +u8 __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op, u32 *prog_id); + int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, @@ -3288,6 +3326,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); extern int netdev_budget; +extern unsigned int netdev_budget_usecs; /* Called by rtnetlink.c:rtnl_unlock() */ void netdev_run_todo(void); @@ -3377,10 +3416,10 @@ static inline void netif_dormant_off(struct net_device *dev) } /** - * netif_dormant - test if carrier present + * netif_dormant - test if device is dormant * @dev: network device * - * Check if carrier is present on device + * Check if device is dormant. */ static inline bool netif_dormant(const struct net_device *dev) { @@ -3801,6 +3840,10 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, extern int netdev_max_backlog; extern int netdev_tstamp_prequeue; extern int weight_p; +extern int dev_weight_rx_bias; +extern int dev_weight_tx_bias; +extern int dev_rx_weight; +extern int dev_tx_weight; bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, @@ -3878,10 +3921,6 @@ void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info); -int netdev_default_l2upper_neigh_construct(struct net_device *dev, - struct neighbour *n); -void netdev_default_l2upper_neigh_destroy(struct net_device *dev, - struct neighbour *n); /* RSS keys are 40 or 52 bytes long */ #define NETDEV_RSS_KEY_LEN 52 @@ -3890,6 +3929,10 @@ void netdev_rss_key_fill(void *buffer, size_t len); int dev_get_nest_level(struct net_device *dev); int skb_checksum_help(struct sk_buff *skb); +int skb_crc32c_csum_help(struct sk_buff *skb); +int skb_csum_hwoffload_help(struct sk_buff *skb, + const netdev_features_t features); + struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, @@ -4061,6 +4104,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } @@ -4163,6 +4207,11 @@ static inline bool netif_is_ovs_master(const struct net_device *dev) return dev->priv_flags & IFF_OPENVSWITCH; } +static inline bool netif_is_ovs_port(const struct net_device *dev) +{ + return dev->priv_flags & IFF_OVS_DATAPATH; +} + static inline bool netif_is_team_master(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM; @@ -4214,6 +4263,11 @@ static inline const char *netdev_name(const struct net_device *dev) return dev->name; } +static inline bool netdev_unregistering(const struct net_device *dev) +{ + return dev->reg_state == NETREG_UNREGISTERING; +} + static inline const char *netdev_reg_state(const struct net_device *dev) { switch (dev->reg_state) { @@ -4334,6 +4388,15 @@ do { \ }) #endif +/* if @cond then downgrade to debug, else print at @level */ +#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \ + do { \ + if (cond) \ + netif_dbg(priv, type, netdev, fmt, ##args); \ + else \ + netif_ ## level(priv, type, netdev, fmt, ##args); \ + } while (0) + #if defined(VERBOSE_DEBUG) #define netif_vdbg netif_dbg #else |